knitr::opts_chunk$set(echo = TRUE)
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.2 ──
## ✔ ggplot2 3.3.6      ✔ purrr   0.3.4 
## ✔ tibble  3.1.8      ✔ dplyr   1.0.10
## ✔ tidyr   1.2.0      ✔ stringr 1.4.1 
## ✔ readr   2.1.2      ✔ forcats 0.5.2 
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
library(ggridges)
weather_df = 
  rnoaa::meteo_pull_monitors(
    c("USW00094728", "USC00519397", "USS0023B17S"),
    var = c("PRCP", "TMIN", "TMAX"), 
    date_min = "2017-01-01",
    date_max = "2017-12-31") %>%
  mutate(
    name = recode(
      id, 
      USW00094728 = "CentralPark_NY", 
      USC00519397 = "Waikiki_HA",
      USS0023B17S = "Waterhole_WA"),
    tmin = tmin / 10,
    tmax = tmax / 10) %>%
  select(name, id, everything())
## Registered S3 method overwritten by 'hoardr':
##   method           from
##   print.cache_info httr
## using cached file: ~/Library/Caches/R/noaa_ghcnd/USW00094728.dly
## date created (size, mb): 2022-09-29 10:42:05 (8.401)
## file min/max dates: 1869-01-01 / 2022-09-30
## using cached file: ~/Library/Caches/R/noaa_ghcnd/USC00519397.dly
## date created (size, mb): 2022-09-29 10:42:17 (1.699)
## file min/max dates: 1965-01-01 / 2020-03-31
## using cached file: ~/Library/Caches/R/noaa_ghcnd/USS0023B17S.dly
## date created (size, mb): 2022-09-29 10:42:22 (0.95)
## file min/max dates: 1999-09-01 / 2022-09-30
weather_df
## # A tibble: 1,095 × 6
##    name           id          date        prcp  tmax  tmin
##    <chr>          <chr>       <date>     <dbl> <dbl> <dbl>
##  1 CentralPark_NY USW00094728 2017-01-01     0   8.9   4.4
##  2 CentralPark_NY USW00094728 2017-01-02    53   5     2.8
##  3 CentralPark_NY USW00094728 2017-01-03   147   6.1   3.9
##  4 CentralPark_NY USW00094728 2017-01-04     0  11.1   1.1
##  5 CentralPark_NY USW00094728 2017-01-05     0   1.1  -2.7
##  6 CentralPark_NY USW00094728 2017-01-06    13   0.6  -3.8
##  7 CentralPark_NY USW00094728 2017-01-07    81  -3.2  -6.6
##  8 CentralPark_NY USW00094728 2017-01-08     0  -3.8  -8.8
##  9 CentralPark_NY USW00094728 2017-01-09     0  -4.9  -9.9
## 10 CentralPark_NY USW00094728 2017-01-10     0   7.8  -6  
## # … with 1,085 more rows
ggplot(weather_df, aes(x = tmin, y = tmax))

ggplot(weather_df, aes(x = tmin, y = tmax)) + 
  geom_point()
## Warning: Removed 15 rows containing missing values (geom_point).

plot_weather = 
  weather_df %>%
  ggplot(aes(x = tmin, y = tmax)) 

plot_weather + geom_point()
## Warning: Removed 15 rows containing missing values (geom_point).

Color mapping apllies to the whole scatter plot

ggplot(weather_df, aes(x = tmin, y = tmax)) + 
  geom_point(aes(color = name))
## Warning: Removed 15 rows containing missing values (geom_point).

ggplot(weather_df, aes(x = tmin, y = tmax)) + 
  geom_point(aes(color = name), alpha = .5) +
  geom_smooth(se = FALSE)
## `geom_smooth()` using method = 'gam' and formula 'y ~ s(x, bs = "cs")'
## Warning: Removed 15 rows containing non-finite values (stat_smooth).
## Warning: Removed 15 rows containing missing values (geom_point).

Color mapping applies to different name

ggplot(weather_df, aes(x = tmin, y = tmax, color = name)) + 
  geom_point(alpha = .3) +
  geom_smooth(se = FALSE)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
## Warning: Removed 15 rows containing non-finite values (stat_smooth).
## Warning: Removed 15 rows containing missing values (geom_point).

make seperate panels

ggplot(weather_df, aes(x = tmin, y = tmax, color = name)) + 
  geom_point(alpha = .3) +
  geom_smooth(se = FALSE) +
  facet_grid(. ~ name)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
## Warning: Removed 15 rows containing non-finite values (stat_smooth).
## Warning: Removed 15 rows containing missing values (geom_point).

  ggplot(weather_df, aes(x = date, y = tmax, color = name)) + 
  geom_point(aes(size = prcp), alpha = .5) +
  geom_smooth(se = FALSE) +
  facet_grid(. ~ name)
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
## Warning: Removed 3 rows containing non-finite values (stat_smooth).
## Warning: Removed 3 rows containing missing values (geom_point).

Learning Accessment

ggplot(weather_df, aes(x = tmax, y = tmin)) + 
  geom_hex()
## Warning: Removed 15 rows containing non-finite values (stat_binhex).

Box plot

weather_df %>% 
  ggplot(aes(x = name, y = tmax, fill = name)) +
  geom_boxplot()
## Warning: Removed 3 rows containing non-finite values (stat_boxplot).

Violin PLot

weather_df %>% 
  ggplot(aes(x = name, y = tmax, fill = name)) +
  geom_violin()
## Warning: Removed 3 rows containing non-finite values (stat_ydensity).

OR

weather_df %>% 
  ggplot(aes(x = tmax, y = name)) +
  geom_density_ridges()
## Picking joint bandwidth of 1.84
## Warning: Removed 3 rows containing non-finite values (stat_density_ridges).

## Saving and embedding plots

First – let’s save a plot

weather_scatterplot = 
  weather_df %>% 
  ggplot(aes(x = date, y = tmax, color = name)) +
  geom_point(aes(size = prcp), alpha = .3) +
  geom_smooth(se = FALSE) +
  facet_grid(. ~ name)

weather_scatterplot
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
## Warning: Removed 3 rows containing non-finite values (stat_smooth).
## Warning: Removed 3 rows containing missing values (geom_point).

ggsave("Results/weather_scatterplot.pdf", weather_scatterplot)
## Saving 7 x 5 in image
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
## Warning: Removed 3 rows containing non-finite values (stat_smooth).
## Removed 3 rows containing missing values (geom_point).
weather_scatterplot
## `geom_smooth()` using method = 'loess' and formula 'y ~ x'
## Warning: Removed 3 rows containing non-finite values (stat_smooth).
## Warning: Removed 3 rows containing missing values (geom_point).